File size: 1,080 Bytes
a12fb0a c530e4b a12fb0a c530e4b a12fb0a c530e4b 7019509 a12fb0a 15aabd2 a12fb0a c530e4b a12fb0a c530e4b a12fb0a c530e4b a12fb0a c530e4b a12fb0a 165da58 a12fb0a |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 |
base_model: huggyllama/llama-7b
base_model_config: huggyllama/llama-7b
model_type: LlamaForCausalLM
tokenizer_type: LlamaTokenizer
load_in_8bit: false
datasets:
- path: openaccess-ai-collective/jeopardy
type: jeopardy
dataset_prepared_path: last_run_prepared
val_set_size: 0.02
adapter:
lora_model_dir:
sequence_len: 512
max_packed_sequence_len:
lora_r:
lora_alpha:
lora_dropout:
lora_target_modules:
lora_fan_in_fan_out: false
wandb_project:
wandb_entity:
wandb_watch:
wandb_run_id:
wandb_log_model:
output_dir: ./jeopardy-bot-7b
gradient_accumulation_steps: 1
micro_batch_size: 1
num_epochs: 3
optimizer: adamw_bnb_8bit
torchdistx_path:
lr_scheduler: cosine
learning_rate: 0.00003
train_on_inputs: false
group_by_length: false
bf16: true
tf32: true
early_stopping_patience:
resume_from_checkpoint:
local_rank:
logging_steps: 5
xformers_attention: true
flash_attention:
gptq_groupsize:
gptq_model_v1:
warmup_steps: 20
eval_steps: 110
save_steps: 660
debug:
deepspeed:
weight_decay: 0.1
fsdp:
fsdp_config:
tokens:
bos_token: "<s>"
eos_token: "</s>"
unk_token: "<unk>"
|